检索结果-内蒙古大学图书馆

1st IEEE Karachi Section Humanitarian Technology Conference, Khi-HTC 2024

作者： Khan, Saadullah Vohra, Sanayna Siddique, Sultan Abdullah Abro, Abdul Ahad Ebrahim, Mansoor Iqra University Main Campus Department of Software Engineering Karachi Pakistan Iqra University Main Campus Department of Computer Science Karachi Pakistan

ISBN: (纸本)9798350373042

This study uses advanced computer vision (CV) and deep learning (DL) techniques to present a combined approach for extensive vehicle detection and number plate recognition. Improving the effectiveness and precision of traffic surveillance and administration systems is the main goal. The two primary parts of the suggested system are identification of number plates recognition and vehicle detection. The vehicle detection module uses rigid images or video streams to recognize along with monitor vehicles in real-time using innovative DL algorithms. Such limitations of system reliability are overcome through the application of CNN and object detection models in an integrated computer vision system that allows for reliable performance under a variety of environmental conditions including unfavorable lighting and weather situations. The goal of an identification plate recognition feature is to read and extract alphanumeric characters from license plates that have been detected. To precisely identify and interpret license plate data, this stage combines DL models with the use of optical character recognition (OCR) techniques. The system can adapt to different geographical locations by supporting changes in plate layouts, fonts, and positions. By combining these two modules, a complete intelligent transportation system solution is produced, offering useful information for applications such as congestion examination, safety, and assurance. Because of its modular architecture, the system is easily scalable and customizable, enabling it to be adjusted to various hardware configurations and surveillance scenarios. Using real-world scenarios and benchmark datasets, extensive experiments are conducted to assess the effectiveness of the proposed system. The outcomes show excellent efficiency and accuracy in tasks involving the detection of vehicles and number plate recognition. By promoting enhanced security, integrity, and general traffic management, the suggested integrated syste

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

System for Table Run Strategy in Peruvian Billiards with Real-Time Oject Detection using YOLOv8n 10

System for Table Run Strategy in Peruvian Billiards with Rea...

引用

10th International Conference on Optimization and Applications, ICOA 2024

作者： Silva, Italo Chavez, Raquel Castillo-Sequera, José Luis Wong, Lenis Peruvian University of Applied Sciences Department of Software Engineering Lima Peru University of Alcalá Department of Computer Science Alcalá de Henares Spain

ISBN: (纸本)9798350387353

The main challenge for billiard players, regardless of their skill level, is to develop a strategy that allows them to consecutively pocket balls in a single turn, commonly known as 'closing the table.' This strategy requires high precision and consistency, especially for less experienced players. This study integrates a YOLOv8n model, a shot suggestion algorithm, and a shot prediction algorithm to build a system that aids players in developing this 'table closing' strategy through visual guides indicating the shots to take and where to position the cue ball for the next shot. The proposed system follows these phases: (1) Selection of the video camera, (2) Selection of the object detection technique, (3) Development of the shot suggestion algorithm, (4) Development of the shot prediction algorithm, and (5) System construction. Phases (1) and (2) address the implementation of the YOLOv8n model, while phases (3) and (4) involve the development of algorithms for the 'table closing' strategy. To validate the system's effectiveness, an experiment with 24 players of different skill levels was conducted, showing that the system reduced the average number of shots needed to close a table to 22, compared to the 47-shot average of professional players. Beginners accepted 100% of the system's recommendations, while intermediate and professional players showed acceptance rates of 95.1% and 95.6%, respectively. A survey indicated high overall satisfaction, with a median response of 4.5 on a 5-point scale. The system also demonstrates significant competitive advantages over existing solutions by maintaining high detection and prediction accuracy while effectively functioning in real-world scenarios, leveraging the latest advances in computer vision to surpass older techniques in both effectiveness and efficiency. © 2024 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Group Recommendation Method Based on Graph Neural Network

Group Recommendation Method Based on Graph Neural Network

引用

2024 International Conference on Cyber-Physical Social Intelligence, ICCSI 2024

作者： Lu, Mengye Zhu, Peng Miao, Chun Wang, Youjian Wang, Jiacun Nanjing University of Science and Technology School of Economics and Management Nanjing China Monmouth University Department of Computer Science and Software Engineering NJ United States

ISBN: (纸本)9798350376739

Group activities are becoming more and more common on the Internet in the big data environment. Which makes many scholars focus on how to recommend items or activities to a group. However, conventional recommendation systems grapple with issues like data sparsity and the cold start problem, which limits the relevance and accuracy of recommendation. Therefore, this paper conducts an in-depth exploration of group recommendation methods utilizing graph neural networks and introduces a novel recommendation framework aimed at enhancing the efficacy of group recommendations. Firstly, this paper discusses how to construct an effective graph structure to encode the social interaction and individual characteristics of users. Then, an improved graph neural network architecture is proposed. Finally, extensive experimental evaluation is carried out on actual datasets, and the findings demonstrate that our framework markedly enhances the accuracy of recommendations. © 2024 IEEE.

关键词： Graph neural network Group recommendation Recommendation system

来源：评论

学校读者我要写书评

暂无评论

Predictive Modeling of Students' Stress Levels Using Machine Learning Algorithm 4

Predictive Modeling of Students' Stress Levels Using Machine...

引用

4th International Conference on Emerging Trends in Networks and computer Communications, ETNCC 2024

作者： Ali, Hassan Amin, M. Hamza Rehman, Attique Ur Javaid, Sabeen Ali, Tahir Muhammad Mir, Azka University of Sialkot Department of Software Engineering Sialkot Pakistan GULF University for Sciences and Technology Department of Computer Science Mubarak Al-Abdullah Kuwait

ISBN: (纸本)9798350353266

The increasing prevalence of stress among university students has raised concern about its impact on academic performance and overall well-being. This conference paper explores the applications of machine learning algorithms to predict and analyze the student's stress level. A comprehensive dataset encompassing various stress-related factors, including academic workload, social interactions, and lifestyle, was collected from Kaggle which consists of 1100 instances and 19 attributes. Our methodology places a premium on human connection, integration of qualitative data to refine the accuracy of stress predictions. By seamlessly merging the capability of machine learning with an empathetic understanding of the human experience, our approach strives to pave the way for a more holistic and personalized educational ecosystem. The insights derived from this study aspire to guide educators, administrators, and policy makers in crafting nurturing environments that empower students to excel both academically and emotionally. Embarking on a journey to unravel the myriad factors influencing students' stress, we consider academic pressures, social dynamics, and personal experiences. Harnessing machine learning algorithms such as decision trees, neural networks, we navigate expansive student populations. Acknowledging the nuanced nature of stress, our study integrates a compassionate approach with cutting-edge technology. The study employs state-of-the-art machine learning techniques using various classification algorithms, to build predictive models for assessing stress levels out of which random forest gives 97.45% accuracy. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

A New Cybersecurity Approach Enhanced by xAI-Derived Rules to Improve Network Intrusion Detection and SIEM

引用

computers, Materials & Continua 2025年第5期83卷 1607-1621页

作者： Federica Uccello Marek Pawlicki Salvatore D'Antonio RafałKozik MichałChoras Centro Direzionale Department of EngineeringUniversity of Naples‘Parthenope’Isola C4Napoli80133Italy Department of Computer and Information Science Software and SystemsLinköping UniversityLinköping58183Sweden ITTI Sp.z o.o. Pozna´n61-612Poland Faculty of Telecommunications Computer Science and Electrical EngineeringBydgoszcz University of Science and TechnologyBydgoszcz85-796Poland

The growing sophistication of cyberthreats,among others the Distributed Denial of Service attacks,has exposed limitations in traditional rule-based Security Information and Event Management *** machine learning–based intrusion detection systems can capture complex network behaviours,their“black-box”nature often limits trust and actionable insight for security *** study introduces a novel approach that integrates Explainable Artificial Intelligence—xAI—with the Random Forest classifier to derive human-interpretable rules,thereby enhancing the detection of Distributed Denial of Service(DDoS)*** proposed framework combines traditional static rule formulation with advanced xAI techniques—SHapley Additive exPlanations and Scoped Rules-to extract decision criteria from a fully trained *** methodology was validated on two benchmark datasets,CICIDS2017 and *** rules were evaluated against conventional Security Information and Event Management Systems rules with metrics such as precision,recall,accuracy,balanced accuracy,and Matthews Correlation *** results demonstrate that xAI-derived rules consistently outperform traditional static ***,the most refined xAI-generated rule achieved near-perfect performance with significantly improved detection of DDoS traffic while maintaining high accuracy in classifying benign traffic across both datasets.

关键词： Cybersecurity explainable artificial intelligence intrusion detection system rule-based SIEM distributed denial of service

来源：评论

学校读者我要写书评

暂无评论

Decentralized Face Identification with Hierarchical Navigable Small World on Blockchain

Decentralized Face Identification with Hierarchical Navigabl...

引用

2023 International Conference on Machine Learning and Automation, CONF-MLA 2023

作者： Lee, Hsiang-Hung Chen, Yiting Department of Computer Science & Information Engineering National Taiwan Normal University Taipei City106 Taiwan Department of Computer Software and Theory Donghua University Shanghai201620 China

This paper presents a novel method for decentralized storage in deep-learning-based face recognition systems using the Hierarchical Navigable Small World (HNSW) algorithm. The proposed solution utilizes Ethereum smart contracts, which acts as highly available data storage systems for storing identifiable data for authorized personnel. In addition, the solution is integrated with a centralized vector database that is in charge of vector indexing, searching and associating face embeddings to an identity on the Ethereum blockchain with anonymous hashes. Vector indexing and search processes involve different machine learning algorithms that enable computations to be carried out in a reasonable time with good matching accuracy. Specifically, we compared different approaches and selected the HNSW algorithm. Accordingly, we successfully implemented a prototype of a reliable and privacy-focused decentralized face identification system for areas under government surveillance, such as customs inspection sites. In our measurements, the system could handle 20,000 face vectors easily with high matching accuracy, and the performance could be further improved using more powerful hardware. Finally, we also propose additional methods to further scale up the system to handle millions of face vectors. © 2024 Institute of Physics Publishing. All rights reserved.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

TezNet: An Efficient Convolutional Neural Network for Optical Coherence Tomography Classification 6

TezNet: An Efficient Convolutional Neural Network for Optica...

引用

6th International Conference on Robotics and Automation in Industry, ICRAI 2024

作者： Qaiser, Muhid Abbas, Muhammad Sohail Muhammad, Asif Haider, Khadija Khan, Haroon National University of Computer and Emerging Sciences Department of Artificial Intelligence and Data Science Islamabad Pakistan National University of Computer and Emerging Sciences Department of Software Engineering Islamabad Pakistan

ISBN: (纸本)9798350355703

Retinal diseases such as Choroidal Neovascularization (CNV), Drusen, and Diabetic Macular Edema (DME) can severely impair vision and are challenging to reverse if detected late. Optical Coherence Tomography (OCT) serves as a non-invasive imaging modality to diagnose these conditions through cross-sectional retinal images. Current advancements in retinal disease detection predominantly focus on fine-tuning larger models to achieve high accuracy, often at the expense of substantial training time and data requirements. We introduce an innovative Convolutional Neural Network (CNN) named TezNet that is deeper and wider than existing custom CNNs for the dataset used in this research yet maintains a lightweight architecture with only 3.6 million parameters. This high efficiency is accomplished by leveraging depthwise and spatial separable convolutional techniques without employing preprocessing techniques or noise reduction filters. The data augmentation techniques generate diverse image qualities, ensuring robust predictions across various scenarios. By training exclusively on a single dataset, our model achieves rapid training times and optimal resource utilization, minimizing the risk of overfitting. This blend of advanced parameter optimization, minimal preprocessing, and strategic data augmentation underscores the potential of our CNN model for swift, precise, and resource-efficient retinal disease detection. TezNet model achieves a remarkable 96% accuracy, competing closely with state-of-the-art networks like ResNet50 (over 23M parameters), InceptionV3 (over 25M parameters), and ResNeXt (89M parameters). © 2024 IEEE.

关键词： Optical coherence tomography

来源：评论

学校读者我要写书评

暂无评论

Variational Auto-Encoder Model and Federated Approach for Non-Intrusive Load Monitoring in Smart Homes 28

Variational Auto-Encoder Model and Federated Approach for No...

引用

28th IEEE Symposium on computers and Communications, ISCC 2023

作者： Kaspour, Shamisa Yassine, Abdulsalam Department of Computer Science Thunder Bay Canada Lakehead University Department of Software Engineering Thunder Bay Canada

ISBN: (纸本)9798350300482

Non-Intrusive Load Monitoring (NILM) is a technique used for identifying individual appliances' energy consumption from a household's total power usage. This study examines a novel energy disaggregation model called Variational Auto-Encoder (VAE) with Federated Learning (FL). Specifically, VAE has a complex structure that resolves the issues in Short Sequence-to-Point (Short S2P) with fewer samples as input windows for each appliance. Short S2P cannot be generalized and might confront some challenges while disaggregating multi-state appliances. To this end, we examine a series of experiments using a real-life dataset of appliance-level power from the UK: UK-DALE. We also investigate additional protection of model parameters using Differential Privacy (DP). The findings show that FL with the VAE model achieves comparable performance to its centralized counterpart and improves all the metrics significantly compared to the Short S2P model. © 2023 IEEE.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Voice Presentation Attacks Detection using Acoustic MLTP Features and BiLSTM 3

Voice Presentation Attacks Detection using Acoustic MLTP Fea...

引用

3rd International Conference on Communication, Computing and Digital Systems, C-CODE 2023

作者： Ibrar, Sundas Javed, Ali Ilyas, Hafsa Uet Taxila Department of Computer Science Punjab Pakistan Uet Taxila Department of Software Engineering Punjab Pakistan

ISBN: (纸本)9798350332391

Automatic speaker verification (ASV) systems have been used in numerous voice-controlled technologies including voice banking, automobiles, smartphones, smart homes, etc. The growth of voice-operated devices is increasing exponentially, and it is mandatory to secure the ASV systems against voice spoofing attacks such as cloned and synthetic voices. The research community has worked to develop spoofing countermeasures to improve the security of ASV systems. However, existing spoofing countermeasures have limitations to detect voice conversion, synthetic speech, and voice replay attacks. There still exists a need for the development of voice spoofing detectors to further strengthen the security of voice-controlled systems. Therefore, in this study, we designed a novel spoofing countermeasure for identifying physical access (PA) and logical access (LA) attacks. More precisely, we proposed a novel acoustic feature descriptor, namely, modified local ternary patterns (MLTP), and used them to train a BiLSTM classifier for voice spoofing detection. We assessed the performance of our approach using the standard ASVspoof-2019 dataset and attained an equal error rate (EER) of 1.87% and 2.66% for the PA and LA attacks, respectively. Experimental results obtained from a detailed assessment signify that our approach has the capability to accurately classify the bonafide and spoofed audio samples over contemporary methods. © 2023 IEEE.

关键词： Automation

来源：评论

学校读者我要写书评

暂无评论

Body Worn Sensors for Health Gaming and e-Learning in Virtual Reality

引用

computers, Materials & Continua 2022年第12期73卷 4763-4777页

作者： Mir Mushhood Afsar Shizza Saqib Yazeed Yasin Ghadi Suliman A.Alsuhibany Ahmad Jalal Jeongmin Park Department of Computer Science Air UniversityIslamabad44000Pakistan Department of Computer Science and Software Engineering Al Ain UniversityAl Ain15551UAE Department of Computer Science College of ComputerQassim UniversityBuraydah51452Saudi Arabia Department of Computer Engineering Tech University of Korea237 Sangidaehak-roSiheung-siGyeonggi-do15073Korea

Virtual reality is an emerging field in the whole *** problem faced by people today is that they are more indulged in indoor technology rather than outdoor ***,the proposed system introduces a fitness solution connecting virtual reality with a gaming interface so that an individual can play first-person *** system proposed in this paper is an efficient and cost-effective solution that can entertain people along with playing outdoor games such as badminton and cricket while sitting in the *** track the human movement,sensors Micro Processor Unit(MPU6050)are used that are connected with Bluetoothmodules andArduino responsible for sending the sensor data to the ***,the sensor data is sent to a machine learning model,which detects the game played by the *** detected game will be operated on human gestures.A publicly available dataset named IM-Sporting Behaviors is initially used,which utilizes triaxial accelerometers attached to the subject’s wrist,knee,and below neck regions to capture important aspects of human *** main objective is that the person is enjoying while playing the game and simultaneously is engaged in some kind of sporting *** proposed system uses artificial neural networks classifier giving an accuracy of 88.9%.The proposed system should apply to many systems such as construction,education,offices and the educational *** experimentation proved the validity of the proposed system.

关键词： Artificial neural networks bluetooth connection inertial sensors machine learning virtual reality exergaming

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：